The flap I had a faithfulness gate on merge: judge scores every case, the mean has to clear 0.80....
LLM-as-judge disagrees with itself between runs
Related
GitLost Is a Preview of Every Agentic Workflow Breach You'll See This Year
Hook A public GitHub issue, a hidden instruction, and one word changed in a prompt was...
LLM-as-judge disagrees with itself between runs
The flap I had a faithfulness gate on merge: judge scores every case, the mean has to clear 0.80....
Context Rollovers Without /compact
How I use Claude Code hooks, a /handoff skill, and HANDOFF.md to keep control over AI coding context rollovers instead of relying on automatic compaction.